The Recognition of Persian Phonemes Using PPNet.

BACKGROUND: In this paper, a novel approach is proposed for the recognition of Persian phonemes in the Persian consonant-vowel combination (PCVC) speech dataset. Nowadays, deep neural networks (NNs) play a crucial role in classification tasks. However, the best results in speech recognition are not yet as perfect as human recognition rate. Deep learning techniques show outstanding performance over many other classification tasks, such as image classification and document classification. Furthermore, the performance is sometimes better than a human. The reason why automatic speech recognition systems are not as qualified as the human speech recognition system, mostly depends on features of data which are fed to deep NNs. METHODS: In this research, first, the sound samples are cut for the exact extraction of phoneme sounds in 50 ms samples. Then, phonemes are divided into 30 groups, containing 23 consonants, 6 vowels, and a silence phoneme. RESULTS: The short-time Fourier transform is conducted on them, and the results are given to PPNet (a new deep convolutional NN architecture) classifier and a total average of 75.87% accuracy is reached which is the best result ever compared to other algorithms on separated Persian phonemes (like in PCVC speech dataset). CONCLUSION: This method not only can be used for recognizing mono-phonemes but it can also be adopted as an input to the selection of the best words in speech transcription.

Assessing the Potential of Thermal Imaging in Recognition of Breast Cancer.

BACKGROUND: Breast cancer is a common disorder in women, constituting one of the main causes of death all over the world. The purpose of this study was to determine the diagnostic value of the breast tissue diseases by the help of thermography. MATERIALS AND METHODS: In this paper, we applied non-contact infrared camera, INFREC R500 for evaluating the capabilities of thermography. The study was conducted on 60 patients suspected of breast disease, who were referred to Imam Khomeini Imaging Center. Information obtained from the questionnaires and clinical examinations along with the obtained diagnostic results from ultrasound images, biopsies and thermography, were analyzed. The results indicated that the use of thermography as well as the asymmetry technique is useful in identifying hypoechoic as well as cystic masses. It should be noted that the patient should not suffer from breast discharge. RESULTS: The accuracy of asymmetry technique identification is respectively 91/89% and 92/30%. Also the accuracy of the exact location of identification is on the 61/53% and 75%. The approach also proved effective in identifying heterogeneous lesions, fibroadenomas, and intraductal masses, but not ISO-echoes and calcified masses. CONCLUSIONS: According to the results of the investigation, thermography may be useful in the initial screening and supplementation of diagnostic procedures due to its safety (its non-radiation properties), low cost and the good recognition of breast tissue disease.

A novel model for smart breast cancer detection in thermogram images.

BACKGROUND: Accuracy in feature extraction is an important factor in image classification and retrieval. In this paper, a breast tissue density classification and image retrieval model is introduced for breast cancer detection based on thermographic images. The new method of thermographic image analysis for automated detection of high tumor risk areas, based on two-directional two-dimensional principal component analysis technique for feature extraction, and a support vector machine for thermographic image retrievalwas tested on 400 images. The sensitivity and specificity of the model are 100% and 98%, respectively.